© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128686
    Prev
    Next
    INDEX
    Explanations

    wall

    np_max-act · gemini-2.0-flash

    information related to safety and reliability standards in gene banking and seed preservation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron spots parts of hyphenated or compound words (i.e. tokens around “-” or “non-,” “near-,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stanley
    -0.06
     polít
    -0.06
     Kenny
    -0.06
     guru
    -0.06
    욱
    -0.06
     for
    -0.06
     Freeman
    -0.06
     нап
    -0.06
     prostate
    -0.06
    oods
    -0.06
    POSITIVE LOGITS
     Вот
    0.07
    jj
    0.07
     skill
    0.06
     (;
    0.06
     Spoj
    0.06
     Оп
    0.06
     MOV
    0.06
     pobl
    0.06
    createQueryBuilder
    0.06
    CreateTime
    0.06
    Activations Density 0.199%

    No Known Activations